Paper Info
Title
Detectability, Uniqueness, and Reliability of Eigen Windows for Stable Verification of Partially Occluded Objects
Abstract
This paper describes a method for recognizing partially occluded objects for bin-picking tasks using eigenspace analysis, referred to as the "eigen window" method, that stores multiple partial appearances of an object in an eigenspace. Such partial appearances require a large amount of memory space. Three measurements, detectability, uniqueness, and reliability, on windows are developed to eliminate redundant windows and thereby reduce memory requirements. Using a pose clustering technique, the method determines the pose of an object and the object type itself. We have implemented the method and verified its validity.
Year
DOI
Venue
1997
10.1109/34.615453
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
occluded object,redundant windows,eigenspace analysis,stores multiple partial appearance,stable verification,eigen windows,memory requirement,bin-picking task,partial appearance,partially occluded objects,memory space,eigen window,object type,eigenspace,computational complexity,history,covariance matrix,object recognition,reliability,image recognition,detectability,image segmentation
Computer vision,Uniqueness,3D single-object recognition,Pattern recognition,Computer science,Object type,Artificial intelligence,Cluster analysis,Eigenvalues and eigenvectors,Computational complexity theory,Cognitive neuroscience of visual object recognition
Journal
Volume
Issue
ISSN
19
9
0162-8828
Citations 
PageRank 
References 
88
31.02
17
Authors
2
Name
Order
Citations
PageRank
kohtaro ohba131766.11
Katsushi Ikeuchi24651881.49